A collection of typical helper functions for python that cannot be found in the however great standard library.
You can install ebbe
with pip with the following command:
pip install ebbe
Iterator functions
- as_chunks
- as_grams
- fail_fast
- uniq
- distinct
- with_prev
- with_prev_and_next
- with_next
- with_is_first
- with_is_last
- without_first
Utilities
Formatting
Decorators
Benchmarking
Iterate over chunks of the desired size by grouping items as we iterate over them.
from ebbe import as_chunks
list(as_chunks(3, [1, 2, 3, 4, 5]))
>>> [[1, 2, 3], [4, 5]]
Iterate over grams (sometimes called n-grams or q-grams etc.) of the given iterable. It works with strings, lists and other sized sequences as well as with lazy iterables without consuming any superfluous memory while doing so.
from ebbe import as_grams
list(as_grams(3, 'hello'))
>>> ['hel', 'ell', 'llo']
list(as_grams(2, (i * 2 for i in range(5))))
>>> [(0, 2), (2, 4), (4, 6), (6, 8)]
Take an iterable (but this has been geared towards generators, mostly), and tries to access the first value to see if an Exception will be raised before returning an equivalent iterator.
This is useful with some badly-conceived generators that checks arguments and raise if they are not valid, for instance, and if you don't want to wrap the whole iteration block within a try/except.
This logic is also available as a decorator.
from ebbe import fail_fast
def hellraiser(n):
if n > 10:
raise TypeError
yield from range(n)
# You will need to do this to catch the error:
gen = hellraiser(15)
try:
for i in gen:
print(i)
except TypeError:
print('Something went wrong when creating the generator')
# With fail_fast
try:
gen = fail_fast(hellraiser(15))
except TypeError:
print('Something went wrong when creating the generator')
for i in gen:
print(i)
Filter repeated items, optionally by key, seen next to each other in the given iterator.
from ebbe import uniq
list(uniq([1, 1, 1, 2, 3, 4, 4, 5, 5, 6]))
>>> [1, 2, 3, 4, 5, 6]
# BEWARE: it does not try to remember items (like the `uniq` command)
list(uniq([1, 2, 2, 3, 2]))
>>> [1, 2, 3, 2]
# Using a key
list(uniq([(1, 2), (1, 3), (2, 4)], key=lambda x: x[0]))
>>> [(1, 2), (2, 4)]
Filter repeated items, optionally by key, in the given iterator.
from ebbe import distinct
list(distinct([0, 3, 4, 4, 1, 0, 3]))
>>> [0, 3, 4, 1]
list(distinct(range(6), key=lambda x: x % 2))
>>> [0, 1]
Iterate over items along with the previous one.
from ebbe import with_prev
for previous_item, item in with_prev(iterable):
print(previous_item, 'came before', item)
list(with_prev([1, 2, 3]))
>>> [(None, 1), (1, 2), (2, 3)]
Iterate over items along with the previous and the next one.
from ebbe import with_prev_and_next
for previous_item, item, next_item in with_prev_and_next(iterable):
print(previous_item, 'came before', item)
print(next_item, 'will come after', item)
list(with_prev_and_next([1, 2, 3]))
>>> [(None, 1, 2), (1, 2, 3), (2, 3, None)]
Iterate over items along with the next one.
from ebbe import with_next
for item, next_item in with_next(iterable):
print(next_item, 'will come after', item)
list(with_next([1, 2, 3]))
>>> [(1, 2), (2, 3), (3, None)]
Iterate over items along with the information that the current item is the first one or not.
from ebbe import with_is_first
for is_first, item in with_is_first(iterable):
if is_first:
print(item, 'is first')
else:
print(item, 'is not first')
list(with_is_first([1, 2, 3]))
>>> [(True, 1), (False, 2), (False, 3)]
Iterate over items along with the information that the current item is the last one or not.
from ebbe import with_is_last
for is_last, item in with_is_last(iterable):
if is_last:
print(item, 'is last')
else:
print(item, 'is not last')
list(with_is_last([1, 2, 3]))
>>> [(False, 1), (False, 2), (True, 3)]
Iterate over the given iterator after skipping its first item. Can be useful if you want to skip headers of a CSV file for instance.
from ebbe import without_first
list(without_first([1, 2, 3]))
>>> [2, 3]
for row in without_first(csv.reader(f)):
print(row)
Operator function similar to operator.getitem
but able to take a default value.
from ebbe import get
get([1, 2, 3], 1)
>>> 2
get([1, 2, 3], 4)
>>> None
# With default value
get([1, 2, 3], 4, 35)
>>> 35
Operator factory similar to operator.itemgetter
but able to take a default value.
from ebbe import getter
get_second_or_thirty = getter(1, 30)
get_second_or_thirty([1, 2, 3])
>>> 2
get_second_or_thirty([1])
>>> 30
# Overriding default on the spot
get_second_or_thirty([1], 76)
>>> 76
Operator function used to retrieve a value at given path in a nested structure or a default value if this value cannot be found.
from ebbe import getpath
data = {'a': {'b': [{'c': 34}, 'test'], 'd': 'hello'}}
getpath(data, ['a', 'b', 0, 'c'])
>>> 34
getpath(data, ['t', 'e', 's', 't'])
>>> None
# Using a default return value
getpath(data, ['t', 'e', 's', 't'], 45)
>>> 45
# Using a string path
getpath(data, 'a.b.d', split_char='.')
>>> 'hello'
Arguments
- target any: target object.
- path iterable: path to get.
- default ?any [
None
]: default value to return. - items ?bool [
True
]: whether to attempt to traverse keys and indices. - attributes ?bool [
False
]: whether to attempt to traverse attributes. - split_char ?str: if given, will split strings passed as path instead of raising
TypeError
. - parse_indices ?bool [
False
]: whether to parse integer indices when splitting string paths.
Function returning a getter function working as getpath and partially applied to use the provided path or paths.
from ebbe import pathgetter
data = {'a': {'b': [{'c': 34}, 'test'], 'd': 'hello'}}
getter = pathgetter(['a', 'b', 0, 'c'])
getter(data)
>>> 34
getter = pathgetter(['t', 'e', 's', 't'])
getter(data)
>>> None
# Using a default return value
getter = pathgetter(['t', 'e', 's', 't'])
getter(data, 45)
>>> 45
# Using a string path
getter = pathgetter('a.b.d', split_char='.')
getter(data)
>>> 'hello'
# Using multiple paths
getter = pathgetter(
['a', 'b', 0, 'c'],
['t', 'e', 's', 't'],
['a', 'b', 'd']
)
getter(data)
>>> (34, None, 'hello')
Arguments
- paths list: paths to get.
- items ?bool [
True
]: whether to attempt to traverse keys and indices. - attributes ?bool [
False
]: whether to attempt to traverse attributes. - split_char ?str: if given, will split strings passed as path instead of raising
TypeError
. - parse_indices ?bool [
False
]: whether to parse integer indices when splitting string paths.
Getter arguments
- target any: target object.
- default ?any [
None
]: default value to return.
Noop function (a function that can be called with any arguments and does nothing). Useful as a default to avoid complicating code sometimes.
from ebbe import noop
noop() # Does nothing...
noop(4, 5) # Still does nothing...
noop(4, index=65) # Nothing yet again...
Function indexing the given iterable in a dict-like structure. This is basically just some functional sugar over a dict
constructor.
from ebbe import indexed
indexed(range(3), key=lambda x: x * 10)
>>> {
0: 0,
10: 1,
20: 2
}
Function grouping the given iterable by a key.
from ebbe import grouped
grouped(range(4), key=lambda x: x % 2)
>>> {
0: [0, 2],
1: [1, 3]
}
# Using an optional value
grouped(range(4), key=lambda x: x % 2, value=lambda x: x * 10)
>>> {
0: [0, 20],
1: [10, 30]
}
# Using the items variant
from ebbe import grouped_items
grouped_items((x % 2, x * 10) for i in range(4))
>>> {
0: [0, 20],
1: [10, 30]
}
Function partitioning the given iterable by key.
from ebbe import partitioned
partitioned(range(4), key=lambda x: x % 2)
>>> [
[0, 2],
[1, 3]
]
# Using an optional value
partitioned(range(4), key=lambda x: x % 2, value=lambda x: x * 10)
>>> [
[0, 20],
[10, 30]
]
# Using the items variant
from ebbe import partitioned_items
partitioned_items((x % 2, x * 10) for i in range(4))
>>> [
[0, 20],
[10, 30]
]
Function sorting the given iterable then dropping its duplicate through a single linear pass over the data.
from ebbe import sorted_uniq
numbers = [3, 17, 3, 4, 1, 4, 5, 5, 1, -1, 5]
sorted_uniq(numbers)
>>> [-1, 1, 3, 4, 5, 17]
# It accepts all of `sorted` kwargs:
sorted_uniq(numbers, reverse=True)
>>> [17, 5, 4, 3, 1, -1]
Function returning the given dictionary with only the selected keys.
from ebbe import pick
# Selected keys must be an iterable:
pick({'a': 1, 'b': 2, 'c': 3}, ['a', 'c'])
>>> {'a': 1, 'c': 3}
# If you need the function to raise of one of the picked keys is not found:
pick({'a': 1, 'b': 2, 'c': 3}, ['a', 'd'])
>>> TypeError
Function returning the given dictionary without the selected keys.
from ebbe import omit
# Selected keys must be a container:
omit({'a': 1, 'b': 2, 'c': 3}, ['a', 'c'])
>>> {'b': 2}
# If need to select large numbers of keys, use a set:
omit({'a': 1, 'b': 2, 'c': 3}, {'a', 'c'})
>>> {'b': 2}
Join function able to group the last items with a custom copula such as "and".
from ebbe import and_join
and_join(['1', '2', '3'])
>>> '1, 2 and 3'
and_join(['1', '2', '3'], separator=';', copula="y")
>>> '1; 2 y 3'
Format given number as an int with thousands separator.
from ebbe import format_int
format_int(4500)
>>> '4,500'
format_int(10000, separator=' ')
>>> '10 000'
Format time with custom precision and unit from years to nanoseconds.
from ebbe import format_time
format_time(57309)
>>> "57 microseconds and 309 nanoseconds"
format_time(57309, precision="microseconds")
>>> "57 microseconds
format_time(78, unit="seconds")
>>> "1 minute and 18 seconds"
format_time(4865268458795)
>>> "1 hour, 21 minutes, 5 seconds, 268 milliseconds, 458 microseconds and 795 nanoseconds"
assert format_time(4865268458795, max_items=2)
>>> "1 hour and 21 minutes"
format_time(4865268458795, short=True)
>>> "1h, 21m, 5s, 268ms, 458µs, 795ns"
Decorate a generator function by wrapping it into another generator function that will fail fast if some validation is run before executing the iteration logic so that exceptions can be caught early.
This logic is also available as a function.
from ebbe.decorators import fail_fast
def hellraiser(n):
if n > 10:
raise TypeError
yield from range(n)
# This will not raise until you consume `gen`
gen = hellraiser(15)
@fail_fast()
def hellraiser(n):
if n > 10:
raise TypeError
yield from range(n)
# This will raise immediately
gen = hellraiser(15)
Decorates a function calling it with a defer
kwarg working a bit like Go's defer statement so that you can "defer" actions to be done by the end of the function or when an exception is raised to cleanup or tear down things.
This relies on an ExitStack and can of course be also accomplished by context managers but this way of declaring things to defer can be useful sometimes to avoid nesting in complex functions.
from ebbe.decorators import with_defer
@with_defer()
def main(content, *, defer):
f = open('./output.txt', 'w')
defer(f.close)
f.write(content)
Context manager printing the time (to stderr by default) it took to execute wrapped code. Very useful to run benchmarks.
from ebbe import Timer
with Timer():
some_costly_operation()
# Will print "Timer: ...s etc." on exit
# To display a custom message:
with Timer('my operation'):
...
# To print to stdout
import sys
with Timer(file=sys.stdout):
...